Font recognition using Variogram fractal dimension

This paper is dealing with font recognition problem in Farsi, Arabic, and English documents. It considers font recognition as texture identification task and the extracted features are independent of document content. The proposed method is based on one of the fractal dimension techniques which is called Variogram Analysis. The average recognition rates using RBF, and KNN classifiers are respectively %95.5, %96 for Farsi fonts, and % 96.9, %98.84 for Arabic fonts, and % 98.21, %99.6 for English fonts. The most important advantages of our algorithm are low feature dimensions, low computational complexity, and high speed compared with the previous efforts.